Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    LaTeX commands and symbols, particularly related to mathematical expressions and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references in square brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestBed
    -0.50
    <tbody>
    -0.48
     purpoſe
    -0.44
    minecraftforge
    -0.44
    şört
    -0.43
     taskId
    -0.43
    Predecesor
    -0.42
    onAttach
    -0.42
    detectChanges
    -0.41
    SupportActionBar
    -0.40
    POSITIVE LOGITS
    <tr>
    1.09
     <<<<<<<<<<<<<<
    0.76
     EconPapers
    0.68
     '{@
    0.51
     estekak
    0.51
    0.49
     Numerade
    0.47
    endcsname
    0.47
    hline
    0.46
    ":[{
    0.45
    Act Density 0.004%

    No Known Activations